Perching on the moving platforms is a promising solution to enhance the endurance and operational range of quadrotors, which could benefit the efficiency of a variety of air-ground cooperative tasks. To ensure robust perching, tracking with a steady relative state and reliable perception is a prerequisite. This paper presents an adaptive dynamic tracking and perching scheme for autonomous quadrotors to achieve tight integration with moving platforms. For reliable perception of dynamic targets, we introduce elastic visibility-aware planning to actively avoid occlusion and target loss. Additionally, we propose a flexible terminal adjustment method that adapts the changes in flight duration and the coupled terminal states, ensuring full-state synchronization with the time-varying perching surface at various angles. A relaxation strategy is developed by optimizing the tangential relative speed to address the dynamics and safety violations brought by hard boundary conditions. Moreover, we take SE(3) motion planning into account to ensure no collision between the quadrotor and the platform until the contact moment. Furthermore, we propose an efficient spatiotemporal trajectory optimization framework considering full state dynamics for tracking and perching. The proposed method is extensively tested through benchmark comparisons and ablation studies. To facilitate the application of academic research to industry and to validate the efficiency of our scheme under strictly limited computational resources, we deploy our system on a commercial drone (DJI-MAVIC3) with a full-size sport-utility vehicle (SUV). We conduct extensive real-world experiments, where the drone successfully tracks and perches at 30~km/h (8.3~m/s) on the top of the SUV, and at 3.5~m/s with 60{\deg} inclined into the trunk of the SUV.

Rules are widely used in Fintech institutions to make fraud prevention decisions, since rules are highly interpretable thanks to their intuitive if-then structure. In practice, a two-stage framework of fraud prevention decision rule set mining is usually employed in large Fintech institutions. This paper is concerned with finding high-quality rule subsets in a bi-objective space (such as precision and recall) from an initial pool of rules. To this end, we adopt the concept of Pareto optimality and aim to find a set of non-dominated rule subsets, which constitutes a Pareto front. We propose a heuristic-based framework called PORS and we identify that the core of PORS is the problem of solution selection on the front (SSF). We provide a systematic categorization of the SSF problem and a thorough empirical evaluation of various SSF methods on both public and proprietary datasets. We also introduce a novel variant of sequential covering algorithm called SpectralRules to encourage the diversity of the initial rule set and we empirically find that SpectralRules further improves the quality of the found Pareto front. On two real application scenarios within Alipay, we demonstrate the advantages of our proposed methodology compared to existing work.

Off-policy evaluation and learning are concerned with assessing a given policy and learning an optimal policy from offline data without direct interaction with the environment. Often, the environment in which the data are collected differs from the environment in which the learned policy is applied. To account for the effect of different environments during learning and execution, distributionally robust optimization (DRO) methods have been developed that compute worst-case bounds on the policy values assuming that the distribution of the new environment lies within an uncertainty set. Typically, this uncertainty set is defined based on the KL divergence around the empirical distribution computed from the logging dataset. However, the KL uncertainty set fails to encompass distributions with varying support and lacks awareness of the geometry of the distribution support. As a result, KL approaches fall short in addressing practical environment mismatches and lead to over-fitting to worst-case scenarios. To overcome these limitations, we propose a novel DRO approach that employs the Wasserstein distance instead. While Wasserstein DRO is generally computationally more expensive compared to KL DRO, we present a regularized method and a practical (biased) stochastic gradient descent method to optimize the policy efficiently. We also provide a theoretical analysis of the finite sample complexity and iteration complexity for our proposed method. We further validate our approach using a public dataset that was recorded in a randomized stoke trial.

Image-Text Matching (ITM) task, a fundamental vision-language (VL) task, suffers from the inherent ambiguity arising from multiplicity and imperfect annotations. Deterministic functions are not sufficiently powerful to capture ambiguity, prompting the exploration of probabilistic embeddings to tackle the challenge. However, the existing probabilistic ITM approach encounters two key shortcomings; the burden of heavy computations due to the Monte Carlo approximation, and the loss saturation issue in the face of abundant false negatives. To overcome the issues, this paper presents an improved Probabilistic Cross-Modal Embeddings (named PCME++) by introducing a new probabilistic distance with a closed-form solution. In addition, two optimization techniques are proposed to enhance PCME++ further: first, the incorporation of pseudo-positives to prevent the loss saturation problem under massive false negatives; second, mixed sample data augmentation for probabilistic matching. Experimental results on MS-COCO Caption and two extended benchmarks, CxC and ECCV Caption, demonstrate the effectiveness of PCME++ compared to state-of-the-art ITM methods. The robustness of PCME++ is also evaluated under noisy image-text correspondences. In addition, the potential applicability of PCME++ in automatic prompt tuning for zero-shot classification is shown. The code is available at https://github.com/naver-ai/pcmepp.

Many water-based optimization metaheuristics have been introduced during the last decade, both for combinatorial and for continuous optimization. Despite the strong similarities of these methods in terms of their underlying natural metaphors (most of them emulate, in some way or another, how drops collaboratively form paths down to the sea), in general the resulting algorithms are quite different in terms of their searching approach or their solution construction approach. For instance, each entity may represent a solution by itself or, alternatively, entities may construct solutions by modifying the landscape while moving. A researcher or practitioner could assume that the degree of similarity between two water-based metaheuristics heavily depends on the similarity of the natural water mechanics they emulate, but this is not the case. In order to bring some clarity to this mosaic of apparently related metaheuristics, in this paper we introduce them, explain their mechanics, and highlight their differences.

Cascading bandits have gained popularity in recent years due to their applicability to recommendation systems and online advertising. In the cascading bandit model, at each timestep, an agent recommends an ordered subset of items (called an item list) from a pool of items, each associated with an unknown attraction probability. Then, the user examines the list, and clicks the first attractive item (if any), and after that, the agent receives a reward. The goal of the agent is to maximize the expected cumulative reward. However, the prior literature on cascading bandits ignores the influences of user states (e.g., historical behaviors) on recommendations and the change of states as the session proceeds. Motivated by this fact, we propose a generalized cascading RL framework, which considers the impact of user states and state transition into decisions. In cascading RL, we need to select items not only with large attraction probabilities but also leading to good successor states. This imposes a huge computational challenge due to the combinatorial action space. To tackle this challenge, we delve into the properties of value functions, and design an oracle BestPerm to efficiently find the optimal item list. Equipped with BestPerm, we develop two algorithms CascadingVI and CascadingBPI, which are both computationally-efficient and sample-efficient, and provide near-optimal regret and sample complexity guarantees. Furthermore, we present experiments to show the improved computational and sample efficiencies of our algorithms compared to straightforward adaptations of existing RL algorithms in practice.

Trajectory optimization is a widely used technique in robot motion planning for letting the dynamics and constraints on the system shape and synthesize complex behaviors. Several previous works have shown its benefits in high-dimensional continuous state spaces and under differential constraints. However, long time horizons and planning around obstacles in non-convex spaces pose challenges in guaranteeing convergence or finding optimal solutions. As a result, discrete graph search planners and sampling-based planers are preferred when facing obstacle-cluttered environments. A recently developed algorithm called INSAT effectively combines graph search in the low-dimensional subspace and trajectory optimization in the full-dimensional space for global kinodynamic planning over long horizons. Although INSAT successfully reasoned about and solved complex planning problems, the numerous expensive calls to an optimizer resulted in large planning times, thereby limiting its practical use. Inspired by the recent work on edge-based parallel graph search, we present PINSAT, which introduces systematic parallelization in INSAT to achieve lower planning times and higher success rates, while maintaining significantly lower costs over relevant baselines. We demonstrate PINSAT by evaluating it on 6 DoF kinodynamic manipulation planning with obstacles.

The Open Radio Access Network (O-RAN) technology has emerged as a promising solution for network operators, providing them with an open and favorable environment. Ensuring effective coordination of x-applications (xAPPs) is crucial to enhance flexibility and optimize network performance within the O-RAN. In this paper, we introduce an innovative approach to the resource allocation problem, aiming to coordinate multiple independent xAPPs for network slicing and resource allocation in O-RAN. Our proposed method focuses on maximizing the weighted throughput among user equipments (UE), as well as allocating physical resource blocks (PRBs). We prioritize two service types, namely enhanced Mobile Broadband and Ultra Reliable Low Latency Communication. To achieve this, we have designed two xAPPs: a power control xAPP for each UE and a PRB allocation xAPP. The proposed method consists of a two-part training phase, where the first part uses supervised learning with a Variational Autoencoder trained to regress the power transmission as well as the user association and PRB allocation decisions, and the second part uses unsupervised learning with a contrastive loss approach to improve the generalization and robustness of the model. We evaluate the performance of our proposed method by comparing its results to those obtained from an exhaustive search algorithm, deep Q-network algorithm, and by reporting performance metrics for the regression task. We also evaluate the proposed model's performance in different scenarios among the service types. The results show that the proposed method is a more efficient and effective solution for network slicing problems compared to state-of-the-art methods.

Offline reinforcement learning (RL) offers a promising direction for learning policies from pre-collected datasets without requiring further interactions with the environment. However, existing methods struggle to handle out-of-distribution (OOD) extrapolation errors, especially in sparse reward or scarce data settings. In this paper, we propose a novel training algorithm called Conservative Density Estimation (CDE), which addresses this challenge by explicitly imposing constraints on the state-action occupancy stationary distribution. CDE overcomes the limitations of existing approaches, such as the stationary distribution correction method, by addressing the support mismatch issue in marginal importance sampling. Our method achieves state-of-the-art performance on the D4RL benchmark. Notably, CDE consistently outperforms baselines in challenging tasks with sparse rewards or insufficient data, demonstrating the advantages of our approach in addressing the extrapolation error problem in offline RL.

In large language models like the Generative Pre-trained Transformer, the Mixture of Experts paradigm has emerged as a powerful technique for enhancing model expressiveness and accuracy. However, deploying GPT MoE models for parallel inference on distributed systems presents significant challenges, primarily due to the extensive Alltoall communication required for expert routing and aggregation. This communication bottleneck exacerbates the already complex computational landscape, hindering the efficient utilization of high-performance computing resources. In this paper, we propose a lightweight optimization technique called ExFlow, to largely accelerate the inference of these MoE models. We take a new perspective on alleviating the communication overhead by exploiting the inter-layer expert affinity. Unlike previous methods, our solution can be directly applied to pre-trained MoE models without any fine-tuning or accuracy degradation. By proposing a context-coherent expert parallelism on distributed systems, our design only uses one Alltoall communication to deliver the same functionality while previous methods all require two Alltoalls. By carefully examining the conditional probability in tokens' routing across multiple layers, we proved that pre-trained GPT MoE models implicitly exhibit a strong inter-layer expert affinity. We then design an efficient integer programming model to capture such features and show that by properly placing the experts on corresponding GPUs, we can reduce up to 67% cross-GPU routing latency. Our solution beats the cutting-edge MoE implementations with experts from 8 to 64, with up to 2.2x improvement in inference throughput. We further provide a detailed study of how the model implicitly acquires this expert affinity at the very early training stage and how this affinity evolves and stabilizes during training.